WO2019097976A1 - 認識システム - Google Patents

認識システム Download PDF

Info

Publication number
WO2019097976A1
WO2019097976A1 PCT/JP2018/039644 JP2018039644W WO2019097976A1 WO 2019097976 A1 WO2019097976 A1 WO 2019097976A1 JP 2018039644 W JP2018039644 W JP 2018039644W WO 2019097976 A1 WO2019097976 A1 WO 2019097976A1
Authority
WO
WIPO (PCT)
Prior art keywords
chip
determination
image
chips
recognition system
Prior art date
Application number
PCT/JP2018/039644
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
泰 重田
Original Assignee
エンゼルプレイングカード株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to AU2018370412A priority Critical patent/AU2018370412A1/en
Priority to CA3082749A priority patent/CA3082749A1/en
Application filed by エンゼルプレイングカード株式会社 filed Critical エンゼルプレイングカード株式会社
Priority to SG11202004469WA priority patent/SG11202004469WA/en
Priority to KR1020207016071A priority patent/KR20200088364A/ko
Priority to EP18877945.8A priority patent/EP3711826A4/en
Priority to JP2019553778A priority patent/JPWO2019097976A1/ja
Priority to US16/764,079 priority patent/US20200388109A1/en
Priority to CN202211444088.7A priority patent/CN116030581A/zh
Priority to CN201880073863.8A priority patent/CN111527528A/zh
Priority to CN202211445290.1A priority patent/CN116013004A/zh
Priority to CN202211445337.4A priority patent/CN116631124A/zh
Publication of WO2019097976A1 publication Critical patent/WO2019097976A1/ja
Priority to PH12020550641A priority patent/PH12020550641A1/en
Priority to US17/891,723 priority patent/US20220398891A1/en
Priority to JP2023060609A priority patent/JP2023085429A/ja
Priority to AU2023229582A priority patent/AU2023229582A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3202—Hardware aspects of a gaming system, e.g. components, construction, architecture thereof
    • G07F17/3216—Construction aspects of a gaming system, e.g. housing, seats, ergonomic aspects
    • G07F17/322—Casino tables, e.g. tables having integrated screens, chip detection means
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3244—Payment aspects of a gaming system, e.g. payment schemes, setting payout ratio, bonus or consolation prizes
    • G07F17/3248—Payment aspects of a gaming system, e.g. payment schemes, setting payout ratio, bonus or consolation prizes involving non-monetary media of fixed value, e.g. casino chips of fixed value
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F1/00—Card games
    • A63F1/06—Card games appurtenances
    • A63F1/067—Tables or similar supporting structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
    • G06K19/04—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the shape
    • G06K19/041—Constructional details
    • G06K19/047—Constructional details the record carrier being shaped as a coin or a gambling token
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/97—Determining parameters from multiple pictures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3202—Hardware aspects of a gaming system, e.g. components, construction, architecture thereof
    • G07F17/3204—Player-machine interfaces
    • G07F17/3206—Player sensing means, e.g. presence detection, biometrics
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3202—Hardware aspects of a gaming system, e.g. components, construction, architecture thereof
    • G07F17/3204—Player-machine interfaces
    • G07F17/3211—Display means
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3225—Data transfer within a gaming system, e.g. data sent between gaming machines and users
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3225—Data transfer within a gaming system, e.g. data sent between gaming machines and users
    • G07F17/3232—Data transfer within a gaming system, e.g. data sent between gaming machines and users wherein the operator is informed
    • G07F17/3237—Data transfer within a gaming system, e.g. data sent between gaming machines and users wherein the operator is informed about the players, e.g. profiling, responsible gaming, strategy/behavior of players, location of players
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3225—Data transfer within a gaming system, e.g. data sent between gaming machines and users
    • G07F17/3232—Data transfer within a gaming system, e.g. data sent between gaming machines and users wherein the operator is informed
    • G07F17/3237—Data transfer within a gaming system, e.g. data sent between gaming machines and users wherein the operator is informed about the players, e.g. profiling, responsible gaming, strategy/behavior of players, location of players
    • G07F17/3239—Tracking of individual players
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3241—Security aspects of a gaming system, e.g. detecting cheating, device integrity, surveillance
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
    • G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
    • G07F17/3286—Type of games
    • G07F17/3293—Card games, e.g. poker, canasta, black jack
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning

Definitions

  • the present invention relates to recognition systems, and more particularly to chip recognition systems.
  • An object of the present invention is to provide a recognition system capable of accurately recognizing an object having a plurality of types.
  • the chip recognition system is A chip recognition system in a game arcade having a game table, A game recording device for recording the state of chips stacked on the gaming table as an image by a camera; A chip determination device that analyzes the image of the recorded chip state to determine the number and type of chips bet by the player; Equipped with The chip determination device stores the feature of the image of the predetermined state of the chip, and when it is determined that the image obtained from the game recording device at the time of determination is the image of the predetermined state, the determination result is determined as unknown. It further has a function of displaying as output.
  • the chip determination device stores, for example, an image in which the accuracy of reading of the chip is lowered as an image in a predetermined state, and an image obtained from the game recording device at the time of determination is
  • an answer is not forcedly output, and that effect is output and displayed as an unknown determination.
  • it is necessary to exclude the determination result (that is, the determination result that is highly likely to be wrong) in the case where an answer is forcedly given to an image that makes the reading accuracy of the chip lower from the determination result of the number and type of chips.
  • the determination result that is, the determination result that is highly likely to be wrong
  • the number and type of chips can be determined only from an image that can be read accurately, and as a result, the chips can be recognized with high accuracy.
  • a chip recognition system is the chip recognition system according to the first aspect, wherein
  • the chip determination device includes an artificial intelligence device, and the artificial intelligence device learns, as teacher data, a plurality of images used for past determination when there is an error in the determination in the chip determination device.
  • the chip determination device self-determines the accuracy of the determination based on the image in which the determination result is erroneous as a result of the learning, and outputs the determination result as a determination result with the determination having no doubt Further have the function of
  • the artificial intelligence device of the chip determination device performs the determination by performing learning using, as teacher data, a plurality of images used in the past (incorrect) determination when there is an error in the determination.
  • the self-determination of the accuracy of H the accuracy of the self-determination can be enhanced. As a result, it is possible to reduce the situation in which an image that can be read correctly is erroneously output and displayed as unknown.
  • a chip recognition system is the chip recognition system according to the second aspect, wherein The chip determination device analyzes the image of the game recording device when it is determined that it is not determined by itself, and the cause of the determination being determined is the overlapping state of the chips stacked on the game table Alternatively, it is further provided with a function of determining and storing whether the cause is that a part of the chip or an entire sheet is hidden by another chip.
  • the dealer can easily confirm the cause of the determination of the determination unknown from the determination result stored in the chip determination device. This allows the dealer to reposition the chip in a position not to be behind other chips, or to reload the jagged chip cleanly (if the player dislikes touching the chip, the dealer should The player may be alerted), and the cause of the determination unknown can be eliminated quickly.
  • a chip recognition system is the chip recognition system according to any one of the first to third aspects, wherein The game recording apparatus assigns an index or time to the image acquired from the camera or applies a tag specifying the stacking state of chips so that the record of the game can be analyzed later by the chip determination apparatus. And record.
  • the chip determination device can easily use the index, time, and tag attached to the image to easily obtain the image of the state of the chip to be analyzed from the recorded contents of the game recording device. It can be identified and the time required for identification can be shortened.
  • a chip recognition system is the chip recognition system according to any one of the first to fourth aspects, wherein
  • the chip determination apparatus includes a second artificial intelligence apparatus, and the second artificial intelligence apparatus determines information of a plurality of images and chips used for past determination when the determination is correct in the chip determination apparatus. Learn as teacher data.
  • the second artificial intelligence device of the chip determination device can be used as teaching data for a plurality of images and chip information used for the past (correct) determination when the determination is correct in the chip determination device.
  • learning it is possible to improve the determination accuracy when determining the number and type of chips.
  • a chip recognition system is the chip recognition system according to any one of the first to fifth aspects, wherein The chip determination apparatus analyzes the image recorded by the camera different from the camera and determines the number and type of chips betted by the player, when the determination is determined to be itself.
  • a chip recognition system is the chip recognition system according to any one of the first to sixth aspects, wherein When the chip determination device recognizes the next chip without recognizing the chip in the vertical direction for a predetermined interval or more, it determines that the image is in the predetermined state, and outputs the result as the determination result as the determination unknown. indicate.
  • a chip recognition system is the chip recognition system according to any one of the first to seventh aspects, wherein The chip determination device compares the number of chips determined from the height of the chips with the number determined by image analysis of the image of the state of the chips, and if different, determines that the image is in the predetermined state A judgment is made, and that effect is output and displayed as a judgment result as a judgment unknown.
  • the recognition system is It is a recognition system which has a plurality of types of judgment objects, judges the objects for each type, and judges the number of each type, A recording device for recording the state of the object as an image by a camera; A determination device including an artificial intelligence device that analyzes the image of the recorded object to determine the number of objects of each type; Equipped with The determination apparatus learns past determination results as teacher data, has a function of self-determining the accuracy in the determination, and determines that the determination results are suspicious if the accuracy level is less than or equal to a certain level. It further has a function of judging and outputting the result as a judgment result as judgment unknown.
  • the determination device learns past determination results as teacher data, and for a new image, first, self-determines the accuracy in the determination, and the level of the accuracy is less than or equal to a certain level In this case, instead of forcing an answer, the output is displayed as unknown.
  • the determination result in the case where an answer is forcedly given to an image whose accuracy in the determination becomes low is excluded from the determination results of the number of objects for each type of object (that is, determination results having a high possibility of mistake).
  • FIG. 1 is a view schematically showing a game arcade provided with a chip recognition system according to an embodiment.
  • FIG. 2 is a diagram for explaining the progress of the baccarat game.
  • FIG. 3 is a block diagram showing a schematic configuration of a chip recognition system according to an embodiment.
  • FIG. 4 is a flowchart for explaining the chip recognition method according to the embodiment.
  • FIG. 5 is a diagram for explaining the case where another chip is hidden behind a certain chip.
  • FIG. 6 is a view for explaining the case where the chips are stacked in a jagged manner.
  • a chip recognition system in a game arcade having a game table will be described as an example of a recognition system for determining an object for each type and determining the number of objects for each type. It goes without saying that the chip is not limited to the chip as long as it has a plurality of types.
  • the game performed in the game arcade having the game table 4 will be described.
  • the gaming table 4 is a baccarat table and a baccarat game is performed will be described, but the present invention can be applied to other game arcades or other games.
  • FIG. 1 is a view schematically showing a game arcade provided with a chip recognition system 10 according to an embodiment.
  • a substantially semicircular gaming table 4 and a plurality of chairs 201 arranged to face the dealer D along the arc side of the gaming table 4 are arranged.
  • the number of chairs 201 is arbitrary, and in the example shown in FIG. 1, six chairs 201 are arranged.
  • bet areas BA are provided on the gaming table 4 corresponding to the chairs 201 respectively. That is, in the illustrated example, six bet areas BA are arranged in an arc.
  • a customer (player) C is seated in each of the chairs 201.
  • the customer (player) C is provided in front of the chair 201 who is seated, which of the player (PLAYER) and the banker (BANKER) will win or become a draw (TIE) as a result of the baccarat game.
  • a bet is made by stacking and arranging chips W in the bet area BA (hereinafter referred to as "bet").
  • the chip W to be bet may be only one type or a plurality of types. Also, the number of chips W to be bet may be arbitrarily determined by the customer (player) C.
  • the chip recognition system 10 recognizes the number and types of chips W stacked and arranged.
  • the dealer D measures timing and calls “No More Bet” and moves the hand in the lateral direction.
  • the dealer D pulls out cards from the card shooter device S onto the game table 4 one by one.
  • the first card is a player (PLAYER)
  • the second card is a banker (BANKER)
  • the third card is a player (PLAYER)
  • the fourth card is a banker (BANKER).
  • the cards are all pulled out of the card shooter apparatus S with the back surface facing upward. Therefore, the rank (number) of cards drawn and the suit (heart, diamond, spade club) can not be grasped from the dealer D or the customer (player) C.
  • customers (players) C who bet on the player (PLAYER) C If there are multiple customers who bet on the PLAYER, the customer C who made the highest bet C, bet on the PLAYER If there are no customers, the dealer D) returns the first and third cards whose back side is upward to the front side.
  • a customer (player) C betting on a banker (BANKER) C a customer C betting the highest bet C if there are multiple customers betting on BANKER, a dealer D if no customer betting on BANKER ) Returns the second and fourth cards to the front (generally, returning the back card to the front is called "squeeze").
  • the fifth card and further the sixth card are drawn by the dealer D, and these are respectively played by the players ( Became a player of PLAYER or BANKER.
  • the time taken until the final result is determined by squeezing the fifth and sixth cards is a time when the customer (player) C is satisfied.
  • the outcome may be determined by the first to fourth cards, and the outcome may be finally determined by the fifth or sixth card.
  • the dealer D grasps that the outcome has been determined and the outcome, and presses the outcome display button on the card shooter device S to inform the customer (player) C of the outcome. Work on the monitor and so on.
  • the outcome of the game is determined by the outcome determination unit of the card shooter device S. It is an error if the dealer D tries to draw more cards without displaying the result of the victory, although the victory or defeat has been decided.
  • the card shooter device S detects the error and an error signal is output.
  • the dealer D settles the chips bet by the customer C, pays the winning customer C, and the player C loses. Collect bet chips. After the settlement is completed, the display of the win / loss results is ended and the betting of the next game is started.
  • the flow of the above-mentioned baccarat game is widely carried out in a general casino, and the card shooter device S is configured to read a drawn card while taking a structure for drawing the card by the hand of the dealer D.
  • the card shooter device S is an existing card shooter device that has a result display button and a result display unit, and has a function of performing win / loss determination and displaying win / loss results.
  • a card shooter device S, a monitor, and the like are arranged for each of the gaming tables 4 arranged in a plurality, and cards to be used are added to each gaming table 4 or a cabinet therebelow in package or set units. Is supplied and operated in cartons.
  • the chip recognition system 10 relates to a system in which a customer (player) C recognizes chips W stacked and arranged in a bet area BA, and more specifically recognizes the number and / or type of chips W. About the system.
  • a monitoring camera 212 for imaging the state of the chips W stacked and arranged in the bet area BA is provided outside the gaming table 4.
  • Each chip W is provided with an RFID
  • the chip tray 23 managed by the dealer D is provided with an RFID reader 22 for reading the RFID of the chip W in the chip tray 23.
  • the chip recognition system 10 is communicably connected to the monitoring camera 212 and the RFID reader 22.
  • FIG. 3 is a block diagram showing a schematic configuration of a chip recognition system 10 according to the present embodiment.
  • the chip recognition system 10 includes a game recording device 11, a chip determination device 12, and a determination correctness determination device 14. Note that at least a part of the chip recognition system 10 is realized by a computer.
  • the game recording device 11 includes, for example, a fixed data storage such as a hard disk.
  • the game recording device 11 records the state of the chips W stacked on the gaming table 4 as an image captured by the camera 212.
  • the image may be a moving image or a continuous still image.
  • the game recording device 11 adds an index or time to the image acquired from the camera 212 so that the game recording can be analyzed later by the chip determination device 12 described later, or a chip W collection scene or payment scene You may assign and record the tag which specifies these.
  • the chip determination device 12 analyzes the image of the state of the chip W recorded in the game recording device 11 to determine the number and types of chips W bet by the customer (player) C.
  • the chip determination device 12 may include an artificial intelligence device that performs image recognition by, for example, deep learning technology.
  • chips W1 to W6 betted by a customer (player) C are stacked in a plurality of piles (see FIG. 5) or when chips W1 to W6 are stacked in a jumbled manner (see FIG. 6) 2.) may not be able to see the entire chip W1 to W6 from the camera 212, so the reading accuracy of the chips W1 to W6 may be low.
  • the chips W1 to W6 are divided into a mountain on the front side and a mountain on the back side. Even if it is included, the chips W1 to W4 on the far side are less likely to be hidden behind the chips W5 and W6 on the near side, but like the camera 212 shown by attaching a symbol (A) in FIG. If the chips W1 to W6 are cluttered and jagged, one chip W1 may be hidden behind another chip W2 above it, or one chip W3 may be behind another chip W4 or W5 above it Hiding makes it difficult to read the entire chips W1 to W6.
  • the conventional artificial intelligence device forcibly gives a (possibly wrong) answer to an image which makes the reading accuracy low, and the answer is wrong.
  • the match between the chip C bet on and the chip tray chip does not match. If matching is not correct due to misreading of the artificial intelligence device, stopping the game one by one will result in inefficiency.
  • the chip determination device 12 in the present embodiment is added to the artificial intelligence device (artificial intelligence device 12 a for chip information determination) for determining the type and the number of stacked chips W. It further includes an artificial intelligence device (artificial intelligence device 12 b for image pattern recognition) that recognizes an image pattern with a low accuracy rate (which is likely to be mistaken).
  • the artificial intelligence device 12a for chip information determination analyzes the image of the state of the chip W recorded in the game recording device 11 to determine the number and type of chips W bet by the customer (player) C.
  • the artificial intelligence device 12a for determining chip information may further determine the position on the betting area BA of the chip W betted by the customer (player) C.
  • the artificial intelligence device 12a for chip information determination analyzes the image of the state of the chip W recorded in the game recording device 11 to determine the number and type of chips W in the chip tray 23 before the settlement of each game. May be
  • the chip determination device 12 outputs the determination result to the output device 15.
  • the output device 15 may output the determination result of the chip determination device 12 to the monitor on the gaming table 4 as character information or may output it to the headset of the dealer D as voice information.
  • the artificial intelligence device 12b for image pattern recognition stores the feature of the image of the predetermined state of the chip W, and determines whether the image obtained from the game recording device 11 is an image of the predetermined state or not. to decide.
  • an image of a predetermined state of the chip W means that when the image is analyzed to determine the number and types of chips, the level of accuracy of the determination may be a certain level or less. That is, it is an image which has doubt in judgment.
  • an image shown by a symbol (B) in FIG. 5
  • an image is stored by imaging and storing the chips W1 to W6 divided into a plurality of mountains by the camera 212 at a low position.
  • the chip determination device 12 determines that the image obtained from the game recording device 11 is an image in a predetermined state by the artificial intelligence device 12b for image pattern recognition, that is, the level of determination accuracy is less than a certain level. Then, when it is judged that it is self-determination, it is outputted as a judgment result to the output device 15 as the judgment result.
  • the chip determination device 12 analyzes the image obtained from the game recording device 11 when the determination is not determined by itself, and causes the determination to be determined unknown is (1) a chip stacked on the gaming table It has a function to judge and memorize whether it is in the overlapping state of (2) or (2) a part or whole of the chip W is in the state of being hidden by another chip. It may be
  • an image obtained from the camera 212 shown by the code (A) or from the camera 212 shown by the code (B) is an image in a predetermined state.
  • the chip W may be read using an image captured by another camera 212 indicated by a symbol (C).
  • the chip W can be viewed more objectively by viewing from other angles with cameras of different orientations or different positions.
  • the chip determination device 12 may output the read result of the chip W using the image captured by each camera 212. In such a case, the chip determination device 12 may output the determination accuracy of each reading result together, or the result with the largest number of readings may be regarded as having a high possibility of being correctly recognized. Good.
  • the determination may not be made when the next chip W is recognized without recognizing the chip in the lump of chips W in the vertical direction for a predetermined interval or more. That is, in the case where the next chip W is recognized without being able to recognize the chip in the vertical direction over a certain interval, there is a high possibility that the chip in the middle is not visible.
  • the chip determination device 12 compares the number of chips W determined from the height of the chips W with the type and number of chips W, and when the determination result of the number is different, the determination can not be made. It may be configured to output the determination result that it is present.
  • the number of sheets may be determined by a method such as triangulation by determining a specific point (such as the center of the outline of the top chip) from the shape of the chip.
  • the determination correctness determination device 14 is a device that determines whether the determination result of the chip determination device 12 is correct. When the settlement of the bet by the customer (player) C is finished, that is, payment to the winning customer (player) C, and the chip W bet by the losing customer (player) C bet When the collection of all the chips is completed, the actual total amount V0 of chips W in the chip tray 23 is grasped.
  • the determination correctness determining device 14 acquires the RFID information of the chip W in the chip tray 23 from the RFID reader 22, and based on the acquired RFID information, the chip tray after the settlement of each game is performed. The type and the number of chips W at 23 are determined, and the actual total amount V0 is grasped.
  • the determination correctness determination device 14 acquires information on the number and type of chips W as a determination result from the chip determination device 12, and a bet guest (player) C bets based on the acquired information on the chips W.
  • the chip determination device 12 obtains the correctness of the determination result of the chip determination device 12 from the determination correctness determination device 14.
  • the artificial intelligence device 12a for the chip information determination is used for the past (correct) determination when the determination is correct.
  • the obtained image and information on the number and types of chips W as the (correct) determination result are learned as teacher data. By repeating such learning, the artificial intelligence device 12a for chip information determination can improve the determination accuracy of the number and types of chips W.
  • the artificial intelligence device 12b for image pattern recognition determines the past (when there is an error in the determination)
  • the image used for the (incorrect) determination is learned as teacher data of "image in a predetermined state".
  • a person sorts out images in a predetermined state such as an image in which one chip is hidden behind another chip, an image of chips stacked on a jagged edge, an image in which halation has occurred, etc.
  • the intelligence device 12b may learn.
  • a person or artificial intelligence intentionally creates an image of a given state (an image in which one chip is behind other chips, an image of jagged chips, an image in which halation has occurred, etc.)
  • the artificial intelligence device 12b for pattern recognition may learn. By repeatedly performing such learning, the artificial intelligence device 12 b for image pattern recognition can accurately extract an image that may have the accuracy of determination not more than a certain level, that is, When self-determining the accuracy, the accuracy of the self-determination can be enhanced.
  • the game recording apparatus 11 is stacked.
  • the state of the chip W is captured and recorded as an image by the camera 212 (step S31).
  • the chip determination device 12 acquires the image recorded in the game recording device 11.
  • the image acquired by the chip determination device 12 is selected based on an index given to the image by the game recording device 11, a time, or a tag specifying a collection scene or a payment scene of the chip W. It is also good.
  • the artificial intelligence device 12b for image pattern recognition determines whether or not the image obtained from the game recording device 11 is an image in a predetermined state (step S32). More specifically, as described above, the artificial intelligence device 12 b for image pattern recognition learns, as teacher data, a plurality of images used for the past determination when there is an error in the determination in the chip determination device 12. Self-determination on the accuracy of the determination of the chip W based on the image in which the determination result is erroneous as a result of the learning, and determines whether the determination accuracy falls below a certain level .
  • the chip determination device 12 determines that the determination is unknown. The effect is output to the output device 15 as a determination result (step S40).
  • the determination result of the chip determination device 12 may be output by the output device 15 as character information to a monitor on the gaming table 4 or may be output as voice information to a headset of the dealer D or the like.
  • the artificial intelligence device 12b for image pattern recognition determines whether the image obtained from the game recording device 11 is an image in a predetermined state (step S33: NO).
  • the artificial intelligence device for chip information determination 12a analyzes the image of the state of the chip W recorded in the game recording device 11 to determine the number and type of chips W bet by the customer (player) C (step S34).
  • step S34 the chip determination device 12 analyzes the image of the state of the chip W recorded in the game recording device 11 and adds it to the number and type of chips W bet by the customer (player) C, The position of the chip W betted by the customer (player) C may be determined, or the number and type of chips W in the chip tray 23 before settlement of each game may be determined.
  • the determination result of the chip determination device 12 may be output by the output device 15 as character information to a monitor on the gaming table 4 or may be output as voice information to a headset of the dealer D or the like.
  • the determination correctness determination device 14 determines whether the determination result of the chip determination device 12 is correct (step S36).
  • step S37 If the determination result of the chip determination device 12 is determined to be correct by the determination correctness determination device 14 (step S37: YES), the image used for the (correct) determination of the chip determination device 12 and the (correct) determination result
  • the information on the number of chips W and the type of chips W is input as teaching data to the artificial intelligence device 12a for determination of chip information, and the artificial intelligence device 12a for determination of chip information performs learning (step S38).
  • the determination correctness determination device 14 determines whether the determination result of the chip determination device 12 is an error (step S37: NO).
  • the image used for the (error) determination of the chip determination device 12 is The artificial intelligence device 12 b for image pattern recognition is input as teacher data of “image in a predetermined state”, and the artificial intelligence device 12 b for image pattern recognition performs learning (step S 39).
  • the chip determination device 12 stores an image that makes the reading accuracy of the chip W lower as an image in a predetermined state, and at the time of determination, the game recording device When it is determined that the image obtained from No. 11 is an image of such a predetermined state, the answer is not forcedly given out, and that effect is output and displayed as an unknown determination.
  • the determination results that is, the determination results having a high possibility of making a mistake
  • the number and type of chips W can be determined only from the image that can be read accurately, and as a result, the chips W can be recognized with high accuracy.
  • the artificial intelligence device 12b for image pattern recognition performs learning using, as teacher data, a plurality of images used in the past (incorrect) determination when there is an error in the determination.
  • the accuracy of the self-determination can be enhanced. As a result, it is possible to reduce the situation in which an image that can originally be read correctly is erroneously displayed as a determination unknown and displayed.
  • the cause of the determination unknown determination is (1) the overlapping state of the chips W stacked on the gaming table 4 (2) Since it is judged and stored which is the cause of the presence of a part of the chip W or the whole of one chip W hidden by another chip W The dealer D can easily confirm the cause. As a result, the dealer D repositions the chip W in a position not to be behind another chip W, or restacks the chip W stacked in a jagged position (a customer (the dealer D touches the chip W) When the player C does not like the player C, the dealer D may warn the customer C), and the cause of the determination unknown can be quickly eliminated.
  • the game recording apparatus 11 adds an index or time to the image acquired from the camera 212 or adds and records a tag specifying the stacked state of the chip W
  • the chip The determination device 12 can easily identify the image of the state of the chip W to be analyzed from the recorded contents of the game recording device 11 by using the index, time and tag attached to the image. The time required for identification can be shortened.
  • the artificial intelligence device 12 a for chip information determination uses a plurality of images and (correct) determinations used in the past (correct) determination when the determination is correct in the chip determination device 12.
  • learning as information on chips W as a result as teacher data, it is possible to improve the determination accuracy when determining the number and types of chips W.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Social Psychology (AREA)
  • Software Systems (AREA)
  • Computer Security & Cryptography (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Mathematical Physics (AREA)
  • Quality & Reliability (AREA)
  • Databases & Information Systems (AREA)
  • Image Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Holo Graphy (AREA)
  • Optical Communication System (AREA)
  • Iron Core Of Rotating Electric Machines (AREA)
  • Pinball Game Machines (AREA)
PCT/JP2018/039644 2017-11-15 2018-10-25 認識システム WO2019097976A1 (ja)

Priority Applications (15)

Application Number Priority Date Filing Date Title
CN201880073863.8A CN111527528A (zh) 2017-11-15 2018-10-25 识别系统
CN202211444088.7A CN116030581A (zh) 2017-11-15 2018-10-25 识别系统
SG11202004469WA SG11202004469WA (en) 2017-11-15 2018-10-25 Recognition system
CA3082749A CA3082749A1 (en) 2017-11-15 2018-10-25 Recognition system
EP18877945.8A EP3711826A4 (en) 2017-11-15 2018-10-25 DETECTION SYSTEM
JP2019553778A JPWO2019097976A1 (ja) 2017-11-15 2018-10-25 認識システム
CN202211445290.1A CN116013004A (zh) 2017-11-15 2018-10-25 识别系统
AU2018370412A AU2018370412A1 (en) 2017-11-15 2018-10-25 Recognition system
KR1020207016071A KR20200088364A (ko) 2017-11-15 2018-10-25 인식 시스템
US16/764,079 US20200388109A1 (en) 2017-11-15 2018-10-25 Recognition system
CN202211445337.4A CN116631124A (zh) 2017-11-15 2018-10-25 识别系统
PH12020550641A PH12020550641A1 (en) 2017-11-15 2020-05-15 Recognition system
US17/891,723 US20220398891A1 (en) 2017-11-15 2022-08-19 Recognition system
JP2023060609A JP2023085429A (ja) 2017-11-15 2023-04-04 認識システム
AU2023229582A AU2023229582A1 (en) 2017-11-15 2023-09-15 Recognition system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017219634 2017-11-15
JP2017-219634 2017-11-15

Related Child Applications (2)

Application Number Title Priority Date Filing Date
US16/764,079 A-371-Of-International US20200388109A1 (en) 2017-11-15 2018-10-25 Recognition system
US17/891,723 Continuation US20220398891A1 (en) 2017-11-15 2022-08-19 Recognition system

Publications (1)

Publication Number Publication Date
WO2019097976A1 true WO2019097976A1 (ja) 2019-05-23

Family

ID=64316378

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/039644 WO2019097976A1 (ja) 2017-11-15 2018-10-25 認識システム

Country Status (10)

Country Link
US (3) US20200388109A1 (ko)
EP (2) EP3711826A4 (ko)
JP (4) JPWO2019097976A1 (ko)
KR (2) KR20200088364A (ko)
CN (8) CN116631124A (ko)
AU (5) AU2018370412A1 (ko)
CA (2) CA3082749A1 (ko)
PH (2) PH12018000374A1 (ko)
SG (5) SG11202004469WA (ko)
WO (1) WO2019097976A1 (ko)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11295431B2 (en) 2019-12-23 2022-04-05 Sensetime International Pte. Ltd. Method and apparatus for obtaining sample images, and electronic device
JP2022546885A (ja) * 2020-08-01 2022-11-10 商▲湯▼国▲際▼私人有限公司 目標対象認識方法及び装置

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116631124A (zh) * 2017-11-15 2023-08-22 天使集团股份有限公司 识别系统
US11205319B2 (en) 2019-06-21 2021-12-21 Sg Gaming, Inc. System and method for synthetic image training of a neural network associated with a casino table game monitoring system
US11183012B2 (en) 2019-08-19 2021-11-23 Sg Gaming, Inc. Systems and methods of automated linking of players and gaming tokens
CN111062237A (zh) * 2019-09-05 2020-04-24 商汤国际私人有限公司 识别图像中的序列的方法及装置、电子设备和存储介质
CN111062401A (zh) * 2019-09-27 2020-04-24 商汤国际私人有限公司 堆叠物体的识别方法及装置、电子设备和存储介质
US11398127B2 (en) 2019-10-07 2022-07-26 Sg Gaming, Inc. Gaming systems and methods using image analysis authentication
US11393282B2 (en) 2019-10-09 2022-07-19 Sg Gaming, Inc. Systems and devices for identification of a feature associated with a user in a gaming establishment and related methods
CN112292689A (zh) * 2019-12-23 2021-01-29 商汤国际私人有限公司 样本图像的获取方法、装置和电子设备
US11861975B2 (en) 2020-03-30 2024-01-02 Lnw Gaming, Inc. Gaming environment tracking optimization
US11495085B2 (en) 2020-07-13 2022-11-08 Sg Gaming, Inc. Gaming environment tracking system calibration
AU2021204557A1 (en) * 2021-05-19 2022-12-08 Sensetime International Pte. Ltd. Methods and devices for comparing objects
CN113557067A (zh) * 2021-06-21 2021-10-26 商汤国际私人有限公司 游戏币状态的检测方法、装置、电子设备和存储介质
CN113748427A (zh) * 2021-09-13 2021-12-03 商汤国际私人有限公司 数据处理方法、装置和系统、介质及计算机设备
CN116157801A (zh) * 2021-09-22 2023-05-23 商汤国际私人有限公司 对象序列的识别方法、网络训练方法、装置、设备及介质
CN115516525A (zh) * 2021-12-15 2022-12-23 商汤国际私人有限公司 状态识别方法、装置、电子设备及计算机可读存储介质
US11967200B2 (en) 2022-01-12 2024-04-23 Lnw Gaming, Inc. Chip tracking system
US11948425B2 (en) 2022-05-06 2024-04-02 Northernvue Corporation Game monitoring device

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008120749A1 (ja) 2007-03-30 2008-10-09 Angel Playing Cards Co., Ltd. Ｒｆｉｄを内包した遊戯用代用貨幣およびその製造方法
US20110052049A1 (en) * 2009-08-26 2011-03-03 Bally Gaming, Inc. Apparatus, method and article for evaluating a stack of objects in an image
JP2014002630A (ja) * 2012-06-20 2014-01-09 System Av Inc コイン選別装置
JP2014068910A (ja) * 2012-09-28 2014-04-21 Glory Ltd 各台装置及び遊技媒体処理方法
JP2016143353A (ja) * 2015-02-04 2016-08-08 エヌ・ティ・ティ・コムウェア株式会社 学習装置、学習方法、およびプログラム
JP2017064386A (ja) * 2015-08-03 2017-04-06 エンゼルプレイングカード株式会社 遊技場における不正検知システム
JP2017109197A (ja) * 2016-07-06 2017-06-22 ウエノテックス株式会社 廃棄物選別システム及びその選別方法
JP2017136347A (ja) * 2015-11-19 2017-08-10 エンゼルプレイングカード株式会社 チップの計測システム

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6848994B1 (en) * 2000-01-17 2005-02-01 Genesis Gaming Solutions, Inc. Automated wagering recognition system
US6683321B2 (en) * 2001-09-28 2004-01-27 Record Products Of America, Inc. Disc counter
GB2382034A (en) * 2001-11-03 2003-05-21 Ian Nigel Davis Betting game scoring and monitoring
US7938722B2 (en) * 2005-09-12 2011-05-10 Igt Enhanced gaming chips and table game security
US7901285B2 (en) * 2004-05-07 2011-03-08 Image Fidelity, LLC Automated game monitoring
US20060160608A1 (en) * 2005-01-14 2006-07-20 Hill Otho D Card game system with automatic bet recognition
US8021231B2 (en) * 2005-12-02 2011-09-20 Walker Digital, Llc Problem gambling detection in tabletop games
AU2008205438B2 (en) * 2007-09-13 2012-07-26 Universal Entertainment Corporation Gaming machine and gaming system using chips
WO2011060486A1 (en) * 2009-11-17 2011-05-26 Tcs John Huxley Australia Pty Limited Roulette performance and analysis
CN102479138A (zh) * 2010-11-29 2012-05-30 鸿富锦精密工业（深圳）有限公司 利用图像进行错误侦测的系统及方法
CN103164713B (zh) * 2011-12-12 2016-04-06 阿里巴巴集团控股有限公司 图像分类方法和装置
CN102663435B (zh) * 2012-04-28 2013-12-11 南京邮电大学 基于半监督的垃圾图片过滤方法
JP6055297B2 (ja) * 2012-12-07 2016-12-27 株式会社日立情報通信エンジニアリング 文字認識装置及び方法、文字認識プログラム
US9646226B2 (en) * 2013-04-16 2017-05-09 The Penn State Research Foundation Instance-weighted mixture modeling to enhance training collections for image annotation
US20160328604A1 (en) * 2014-01-07 2016-11-10 Arb Labs Inc. Systems and methods of monitoring activities at a gaming venue
JP6528147B2 (ja) * 2014-01-31 2019-06-12 株式会社日本デジタル研究所 会計データ入力支援システム、方法およびプログラム
CN103927387B (zh) * 2014-04-30 2017-06-16 成都理想境界科技有限公司 图像检索系统及其相关方法和装置
CN105740751A (zh) * 2014-12-11 2016-07-06 深圳市赛为智能股份有限公司 一种目标检测与识别的方法和系统
CA2947969C (en) * 2015-05-29 2017-09-26 Adrian BULZACKI Systems, methods and devices for monitoring betting activities
CN106909552A (zh) * 2015-12-22 2017-06-30 成都理想境界科技有限公司 图像检索服务器、系统、相关检索及排错方法
CN107239786B (zh) * 2016-03-29 2022-01-11 阿里巴巴集团控股有限公司 一种字符识别方法和装置
CN106815323B (zh) * 2016-12-27 2020-02-07 西安电子科技大学 一种基于显著性检测的跨域视觉检索方法
CN116631124A (zh) * 2017-11-15 2023-08-22 天使集团股份有限公司 识别系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008120749A1 (ja) 2007-03-30 2008-10-09 Angel Playing Cards Co., Ltd. Ｒｆｉｄを内包した遊戯用代用貨幣およびその製造方法
US20110052049A1 (en) * 2009-08-26 2011-03-03 Bally Gaming, Inc. Apparatus, method and article for evaluating a stack of objects in an image
JP2014002630A (ja) * 2012-06-20 2014-01-09 System Av Inc コイン選別装置
JP2014068910A (ja) * 2012-09-28 2014-04-21 Glory Ltd 各台装置及び遊技媒体処理方法
JP2016143353A (ja) * 2015-02-04 2016-08-08 エヌ・ティ・ティ・コムウェア株式会社 学習装置、学習方法、およびプログラム
JP2017064386A (ja) * 2015-08-03 2017-04-06 エンゼルプレイングカード株式会社 遊技場における不正検知システム
JP2017136347A (ja) * 2015-11-19 2017-08-10 エンゼルプレイングカード株式会社 チップの計測システム
JP2017109197A (ja) * 2016-07-06 2017-06-22 ウエノテックス株式会社 廃棄物選別システム及びその選別方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3711826A4

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11295431B2 (en) 2019-12-23 2022-04-05 Sensetime International Pte. Ltd. Method and apparatus for obtaining sample images, and electronic device
JP2022522078A (ja) * 2019-12-23 2022-04-14 商▲湯▼国▲際▼私人有限公司 サンプル画像取得方法、装置、及び電子デバイス
JP2022546885A (ja) * 2020-08-01 2022-11-10 商▲湯▼国▲際▼私人有限公司 目標対象認識方法及び装置

Also Published As

Publication number Publication date
AU2018370412A1 (en) 2020-06-18
SG11202004469WA (en) 2020-06-29
US20190147689A1 (en) 2019-05-16
CN115810142A (zh) 2023-03-17
PH12018000374A1 (en) 2019-06-24
CN116631124A (zh) 2023-08-22
KR20190055747A (ko) 2019-05-23
JP2023159365A (ja) 2023-10-31
AU2018263987A1 (en) 2019-05-30
US20220398891A1 (en) 2022-12-15
EP3486883A1 (en) 2019-05-22
SG10201913894VA (en) 2020-03-30
CN115810141A (zh) 2023-03-17
AU2020207871A1 (en) 2020-08-13
SG10201913891TA (en) 2020-03-30
SG10201913892SA (en) 2020-03-30
JP2019088775A (ja) 2019-06-13
CA3082749A1 (en) 2019-05-23
EP3711826A1 (en) 2020-09-23
CN116030581A (zh) 2023-04-28
US20200388109A1 (en) 2020-12-10
EP3711826A4 (en) 2021-09-22
KR20200088364A (ko) 2020-07-22
CN111527528A (zh) 2020-08-11
CN116013004A (zh) 2023-04-25
JPWO2019097976A1 (ja) 2020-11-19
JP2023085429A (ja) 2023-06-20
AU2022231800A1 (en) 2022-10-13
CA3024036A1 (en) 2019-05-15
SG10201913895QA (en) 2020-03-30
PH12020550641A1 (en) 2021-03-08
CN115810143A (zh) 2023-03-17
CN109771931A (zh) 2019-05-21
AU2023229582A1 (en) 2023-10-05

Similar Documents

Publication Publication Date Title
WO2019097976A1 (ja) 認識システム
US20230394362A1 (en) Chip recognizing and learning system
JPWO2018139303A1 (ja) チップ認識システム
NZ739329A (en) Chip recognizing and learning system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18877945

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019553778

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 3082749

Country of ref document: CA

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20207016071

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2018370412

Country of ref document: AU

Date of ref document: 20181025

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2018877945

Country of ref document: EP

Effective date: 20200615